Smart Patient Monitoring System

The increasing burden of chronic illnesses and the demand for uninterrupted medical supervision have intensified the pursuit of intelligent healthcare technologies capable of continuous patient observation. Conventional monitoring approaches rely on intermittent manual assessment, which is often limited by delayed response, human error, and restricted accessibility to real-time clinical data. To overcome these constraints, this work proposes a Smart Patient Monitoring System that integrates Internet of Things (IoT) sensing, cloud-assisted communication, and machine learning-driven analytics for proactive healthcare support. The system utilizes biomedical and environmental sensors interfaced with a Raspberry Pi to continuously measure vital parameters such as body temperature, blood oxygen saturation (SpO₂), pulse rate, and humidity. The collected data are wirelessly transmitted to a cloud platform, where they are visualized through an interactive dashboard with automated emergency notifications. The implementation is carried out in two phases: Phase-1 focuses on the development of a real-time IoT monitoring architecture with alert generation, whereas Phase-2 incorporates predictive analytics using algorithms such as Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) for early detection of abnormal physiological trends. Experimental observations demonstrate that LSTM effectively captures temporal variations in health signals, offering improved predictive performance. The proposed system enhances patient safety through timely intervention, remote accessibility, and data-driven decision support, making it suitable for hospital, home-care, and elderly monitoring applications.